# mayank14211/grace_voice_agent architecture

> Architecture diagram of the GitHub repository mayank14211/grace_voice_agent, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-19). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mayank14211/grace_voice_agent
- Repository: https://github.com/mayank14211/grace_voice_agent

## Overview

GRACE is a voice-controlled desktop assistant. The main workflow is a user speaking a wake word and command, which the controller routes to a capability and reports through speech. The README also documents screen reading, selected-text code analysis, dictation, system control, and AI image generation. The excerpts show module implementations and imports, but not all controller dispatch details; edges are limited to documented or indexed relationships. Hand-gesture control appears as a separate implementation, with no shown connection to the main workflow.

Main entry points: [`main.py`](https://github.com/mayank14211/grace_voice_agent/blob/main/main.py) (Main controller), [`screen_reader.py`](https://github.com/mayank14211/grace_voice_agent/blob/main/screen_reader.py) (Screen reader), [`speech_recognition_module.py`](https://github.com/mayank14211/grace_voice_agent/blob/main/speech_recognition_module.py) (Speech recognition), [`system_control.py`](https://github.com/mayank14211/grace_voice_agent/blob/main/system_control.py) (System control)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interaction["Voice interaction"]
  node_controller["Main controller<br/>[main.py]"]
  node_speech["Speech recognition"]
  node_speech_output["Text to speech<br/>[tts.py]"]
end

subgraph group_capabilities["Assistant capabilities"]
  node_system["System control<br/>[system_control.py]"]
  node_reader["Screen reader<br/>[screen_reader.py]"]
  node_code_analysis["Code analysis<br/>[screen_reader.py]"]
  node_image_generation["Image generation<br/>[main.py]"]
end

subgraph group_integrations["External integrations"]
  node_microphone(("Microphone"))
  node_desktop["Desktop environment"]
  node_ocr["Tesseract OCR"]
  node_gemini["Gemini AI"]
  node_image_service["AI image service"]
  node_webcam(("Webcam"))
end

subgraph group_gesture["Gesture control"]
  node_gesture_controller["Gesture controller<br/>[Hand_Gesture.py]"]
end

node_user(("User"))

node_user -->|"speaks commands"| node_microphone
node_microphone -->|"provides audio"| node_speech
node_speech -->|"transcribes commands"| node_controller
node_controller -->|"routes commands"| node_system
node_controller -->|"routes reading requests"| node_reader
node_controller -->|"routes analysis requests"| node_code_analysis
node_controller -->|"handles generation"| node_image_generation
node_controller -->|"speaks responses"| node_speech_output
node_reader -->|"extracts screen text"| node_ocr
node_reader -->|"captures screen"| node_desktop
node_code_analysis -->|"analyzes code"| node_gemini
node_system -->|"controls applications"| node_desktop
node_image_generation -->|"requests images"| node_image_service
node_webcam -->|"supplies frames"| node_gesture_controller
node_gesture_controller -->|"controls pointer"| node_desktop

click node_controller "https://github.com/mayank14211/grace_voice_agent/blob/main/main.py"
click node_speech "https://github.com/mayank14211/grace_voice_agent/blob/main/speech_recognition_module.py"
click node_speech_output "https://github.com/mayank14211/grace_voice_agent/blob/main/tts.py"
click node_system "https://github.com/mayank14211/grace_voice_agent/blob/main/system_control.py"
click node_reader "https://github.com/mayank14211/grace_voice_agent/blob/main/screen_reader.py"
click node_code_analysis "https://github.com/mayank14211/grace_voice_agent/blob/main/screen_reader.py"
click node_image_generation "https://github.com/mayank14211/grace_voice_agent/blob/main/main.py"
click node_gesture_controller "https://github.com/mayank14211/grace_voice_agent/blob/main/Hand_Gesture.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_controller,node_speech,node_speech_output,node_user toneBlue
class node_system,node_reader,node_code_analysis,node_image_generation toneAmber
class node_microphone,node_desktop,node_ocr,node_gemini,node_image_service,node_webcam toneMint
class node_gesture_controller toneRose
```

## Components

### Voice interaction

- [Main controller](https://github.com/mayank14211/grace_voice_agent/blob/main/main.py): `main.py`
- [Speech recognition](https://github.com/mayank14211/grace_voice_agent/blob/main/speech_recognition_module.py): `speech_recognition_module.py`
- [Text to speech](https://github.com/mayank14211/grace_voice_agent/blob/main/tts.py): `tts.py`

### Assistant capabilities

- [System control](https://github.com/mayank14211/grace_voice_agent/blob/main/system_control.py): `system_control.py`
- [Screen reader](https://github.com/mayank14211/grace_voice_agent/blob/main/screen_reader.py): `screen_reader.py`
- [Code analysis](https://github.com/mayank14211/grace_voice_agent/blob/main/screen_reader.py): `screen_reader.py`
- [Image generation](https://github.com/mayank14211/grace_voice_agent/blob/main/main.py): `main.py`

### External integrations

- **Microphone**
- **Desktop environment**
- **Tesseract OCR**
- **Gemini AI**
- **AI image service**
- **Webcam**

### Gesture control

- [Gesture controller](https://github.com/mayank14211/grace_voice_agent/blob/main/Hand_Gesture.py): `Hand_Gesture.py`

### Other components

- **User**

## Connections

- User → Microphone: speaks commands (evidence: `README.md`)
- Microphone → Speech recognition: provides audio (evidence: `speech_recognition_module.py`)
- Speech recognition → Main controller: transcribes commands (evidence: `README.md`)
- Main controller → System control: routes commands (evidence: `README.md`)
- Main controller → Screen reader: routes reading requests (evidence: `README.md`)
- Main controller → Code analysis: routes analysis requests (evidence: `README.md`)
- Main controller → Image generation: handles generation (evidence: `main.py`)
- Main controller → Text to speech: speaks responses (evidence: `main.py`)
- Screen reader → Tesseract OCR: extracts screen text (evidence: `screen_reader.py`)
- Screen reader → Desktop environment: captures screen (evidence: `screen_reader.py`)
- Code analysis → Gemini AI: analyzes code (evidence: `README.md`)
- System control → Desktop environment: controls applications (evidence: `system_control.py`)
- Image generation → AI image service: requests images (evidence: `main.py`)
- Webcam → Gesture controller: supplies frames (evidence: `Hand_Gesture.py`)
- Gesture controller → Desktop environment: controls pointer (evidence: `Hand_Gesture.py`)
